steipete-cli-builder

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime LLM context can be fed outsider-authored free text via the process <input> command’s “Input file or URL” path, where the tool may fetch/scrape arbitrary public web content or read downloaded files and then pass that content into the AI provider for generation.